# vlm
標記為「vlm」的 24 篇文章
Multimodal Security Practice Exam
Practice exam covering image injection, audio attacks, cross-modal transfer, and document parsing exploitation.
Multimodal Security
Security assessment of multimodal AI systems processing images, audio, video, and cross-modal inputs, covering vision-language models, speech systems, video analysis, and cross-modal attack techniques.
Benchmarking Multimodal Model Safety
Designing and implementing safety benchmarks for multimodal AI models that process images, audio, and video alongside text, covering cross-modal attack evaluation, consistency testing, and safety score aggregation.
Attacks on Vision-Language Models
Comprehensive techniques for attacking vision-language models including GPT-4V, Claude vision, and Gemini, covering adversarial images, typographic exploits, and multimodal jailbreaks.
Adversarial Image Examples for VLMs
Pixel-level perturbations that change VLM behavior, including PGD attacks on vision encoders, transferable adversarial images, and patch attacks.
VLM Architecture & Vision-Language Alignment
Deep dive into VLM architectures including CLIP, SigLIP, and vision transformers. How image patches become tokens, alignment training, and where misalignment creates exploitable gaps.
Image-Based Prompt Injection
Techniques for embedding text instructions in images to manipulate VLMs, including steganographic injection, visible text attacks, and QR code exploitation.
Vision-Language Model Attacks
Comprehensive overview of the VLM attack surface, how vision encoders connect to language models, and why multimodal systems create new injection vectors.
Lab: Crafting Image-Based Injections
Hands-on lab for creating image-based prompt injections, testing against VLMs, and measuring success rates across different injection techniques.
OCR & Typographic Attacks
Exploiting OCR capabilities in VLMs through typographic attacks, font manipulation, adversarial text overlays, and text rendering exploits.
Typographic Adversarial Attacks
How text rendered in images influences VLM behavior: adversarial typography, font-based prompt injection, visual instruction hijacking, and defenses against typographic manipulation.
VLM-Specific Jailbreaking
Jailbreaking techniques that exploit the vision modality, including image-text inconsistency attacks, visual safety bypass, and cross-modal jailbreaking strategies.
Multimodal 安全 Practice Exam
Practice exam covering image injection, audio attacks, cross-modal transfer, and document parsing exploitation.
多模態安全
處理影像、音訊、影片與跨模態輸入之多模態 AI 系統的安全評估，涵蓋視覺-語言模型、語音系統、影片分析與跨模態攻擊技術。
Benchmarking Multimodal 模型 Safety
Designing and implementing safety benchmarks for multimodal AI models that process images, audio, and video alongside text, covering cross-modal attack evaluation, consistency testing, and safety score aggregation.
攻擊s on Vision-Language 模型s
Comprehensive techniques for attacking vision-language models including GPT-4V, Claude vision, and Gemini, covering adversarial images, typographic exploits, and multimodal jailbreaks.
VLM 的對抗性影像範例
會改變 VLM 行為的像素級擾動，包括針對視覺編碼器的 PGD 攻擊、可遷移對抗影像，以及 patch 攻擊。
VLM 架構與視覺—語言對齊
深入探討 VLM 架構，包括 CLIP、SigLIP 與 vision transformers。圖像 patch 如何變成 token、對齊訓練，以及錯位（misalignment）如何製造可利用之缺口。
以圖像為本之提示注入
將文字指令嵌入圖像以操弄 VLM 之技術，含隱寫注入、可見文字攻擊與 QR 碼利用。
視覺-語言模型
視覺-語言模型（VLM）的安全評估——涵蓋 VLM 架構、圖片注入技術、OCR 與字型攻擊、對抗性圖片生成與 VLM 特定越獄。
實驗室: Crafting Image-Based Injections
Hands-on lab for creating image-based prompt injections, testing against VLMs, and measuring success rates across different injection techniques.
OCR 與排版攻擊
經由排版攻擊、字體操弄、對抗文字覆蓋，與文字渲染利用來利用 VLM 中之 OCR 能力。
Typographic Adversarial 攻擊s
How text rendered in images influences VLM behavior: adversarial typography, font-based prompt injection, visual instruction hijacking, and defenses against typographic manipulation.
VLM 特有的越獄手法
利用視覺模態的越獄技術，包括影像─文字不一致攻擊、視覺安全繞過，以及跨模態越獄策略。